EUVIMEDEUVIMED entdecken
Crossref

Leveraging Reviewer Experience in Code Review Comment Generation

Hong Yi Lin, Patanamon Thongtanunam, Christoph Treude, Michael W. Godfrey, Chunhua Liu, Wachiraphan Charoenwet

ACM Transactions on Software Engineering and Methodology · 31.05.2026 · 35 (5) · 1-34

DOI: 10.1145/3762183 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 24.04.2026. Verfasst von Hong Yi Lin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 100 Literaturangaben. Gefördert von: Australian Research Council’s Discovery Early Career Researcher Award.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modern code review is a ubiquitous software quality assurance process aimed at identifying and resolving potential issues (e.g., functional, evolvability) within newly written code. Despite its effectiveness, the process demands large amounts of effort from the human reviewers involved. To help alleviate this workload, researchers have trained various deep learning-based language models to imitate human reviewers in providing natural language code reviews for submitted code. Formally, this automation task is known as code review comment generation. Prior work has demonstrated improvements in code review comment generation by leveraging machine learning techniques and neural models, such as transfer learning and the transformer architecture. However, the quality of the model-generated reviews remains sub-optimal due to the quality of the open-source code review data used in model training. This is in part due to the data obtained from open-source projects where code reviews are conducted in a public forum, and reviewers possess varying levels of software development experience, potentially affecting the quality of their feedback. To accommodate this variation, we propose a suite of experience-aware training methods that utilise the reviewers’ past authoring and reviewing experiences as signals for review quality. Specifically, we propose experience-aware loss functions (ELF), which use the reviewers’ authoring and reviewing ownership of a project as weights in the model’s loss function. Through this method, experienced reviewers’ code reviews yield larger influence over the model’s behaviour. Compared to the SOTA model, ELF was able to generate higher quality reviews in terms of accuracy (e.g., +29% applicable comments), informativeness (e.g., +56% suggestions), and issue types discussed (e.g., +129% functional issues identified). The key contribution of this work is the demonstration of how traditional software engineering concepts such as reviewer experience can be integrated into the design of AI-based automated code review models.

Förderung

  • Australian Research Council’s Discovery Early Career Researcher Award

Zitieren

APA

Lin, H. Y., Thongtanunam, P., Treude, C., Godfrey, M. W., Liu, C., & Charoenwet, W. (2026). Leveraging Reviewer Experience in Code Review Comment Generation. ACM Transactions on Software Engineering and Methodology, 35(5), 1-34. https://doi.org/10.1145/3762183

Vancouver

Lin HY, Thongtanunam P, Treude C, Godfrey MW, Liu C, Charoenwet W. Leveraging Reviewer Experience in Code Review Comment Generation. ACM Transactions on Software Engineering and Methodology. 2026;35(5):1-34. doi:10.1145/3762183

BibTeX
@article{Lin2026,
  author = {Lin, Hong Yi and Thongtanunam, Patanamon and Treude, Christoph and Godfrey, Michael W. and Liu, Chunhua and Charoenwet, Wachiraphan},
  title = {Leveraging Reviewer Experience in Code Review Comment Generation},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2026},
  volume = {35},
  number = {5},
  pages = {1--34},
  doi = {10.1145/3762183}
}
Kostenlos starten →